Generalized Strategic Classification and the Case of Aligned Incentives

• URL: http://arxiv.org/abs/2202.04357v1
• Date: Wed, 9 Feb 2022 09:36:09 GMT
• Title: Generalized Strategic Classification and the Case of Aligned Incentives
• Authors: Sagi Levanon and Nir Rosenfeld
• Abstract summary: We argue for a broader perspective on what accounts for strategic user behavior. Our model subsumes most current models, but includes other novel settings. We show how our results and approach can extend to the most general case.
• Score: 16.607142366834015
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicative machine learning models are frequently being used by companies, institutes and organizations to make choices about humans. Strategic classification studies learning in settings where self-interested users can strategically modify their features to obtain favorable predictive outcomes. A key working assumption, however, is that 'favorable' always means 'positive'; this may be appropriate in some applications (e.g., loan approval, university admissions and hiring), but reduces to a fairly narrow view what user interests can be. In this work we argue for a broader perspective on what accounts for strategic user behavior, and propose and study a flexible model of generalized strategic classification. Our generalized model subsumes most current models, but includes other novel settings; among these, we identify and target one intriguing sub-class of problems in which the interests of users and the system are aligned. For this cooperative setting, we provide an in-depth analysis, and propose a practical learning approach that is effective and efficient. We compare our approach to existing learning methods and show its statistical and optimization benefits. Returning to our fully generalized model, we show how our results and approach can extend to the most general case. We conclude with a set of experiments that empirically demonstrate the utility of our approach.

Related papers

• Towards a Unified View of Preference Learning for Large Language Models: A Survey [88.66719962576005]
  Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. We decompose all the strategies in preference learning into four components: model, data, feedback, and algorithm.
  arXiv  Detail & Related papers  (2024-09-04T15:11:55Z)
• Classification Under Strategic Self-Selection [13.168262355330299]
  We study the effects of self-selection on learning and the implications of learning on the composition of the self-selected population. We propose a differentiable framework for learning under self-selective behavior, which can be optimized effectively.
  arXiv  Detail & Related papers  (2024-02-23T11:37:56Z)
• Scalable and Equitable Math Problem Solving Strategy Prediction in Big Educational Data [2.86829428083307]
  We develop an embedding called MVec where we learn a representation based on the mastery of students. We then cluster these embeddings with a non-parametric clustering method. We show that our approach can scale up to achieve high accuracy by training on a small sample of a large dataset.
  arXiv  Detail & Related papers  (2023-08-07T19:51:10Z)
• MERMAIDE: Learning to Align Learners using Model-Based Meta-Learning [62.065503126104126]
  We study how a principal can efficiently and effectively intervene on the rewards of a previously unseen learning agent in order to induce desirable outcomes. This is relevant to many real-world settings like auctions or taxation, where the principal may not know the learning behavior nor the rewards of real people. We introduce MERMAIDE, a model-based meta-learning framework to train a principal that can quickly adapt to out-of-distribution agents.
  arXiv  Detail & Related papers  (2023-04-10T15:44:50Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• Strategic Classification with Graph Neural Networks [10.131895986034316]
  Using a graph for learning introduces inter-user dependencies in prediction. We propose a differentiable framework for strategically-robust learning of graph-based classifiers.
  arXiv  Detail & Related papers  (2022-05-31T13:11:25Z)
• Contrastive Learning for Fair Representations [50.95604482330149]
  Trained classification models can unintentionally lead to biased representations and predictions. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. We propose a method for mitigating bias by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations.
  arXiv  Detail & Related papers  (2021-09-22T10:47:51Z)
• Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference [71.11416263370823]
  We propose a generative inverse reinforcement learning for user behavioral preference modelling. Our model can automatically learn the rewards from user's actions based on discriminative actor-critic network and Wasserstein GAN.
  arXiv  Detail & Related papers  (2021-05-03T13:14:25Z)
• Strategic Classification Made Practical [8.778578967271866]
  We present a learning framework for strategic classification that is practical. Our approach directly minimizes the "strategic" empirical risk, achieved by differentiating through the strategic response of users. A series of experiments demonstrates the effectiveness of our approach on various learning settings.
  arXiv  Detail & Related papers  (2021-03-02T16:03:26Z)
• Predicting Engagement in Video Lectures [24.415345855402624]
  We introduce a novel, large dataset of video lectures for predicting context-agnostic engagement. We propose both cross-modal and modality-specific feature sets to achieve this task. We demonstrate the use of our approach in the case of data scarcity.
  arXiv  Detail & Related papers  (2020-05-31T19:28:16Z)
• Three Approaches for Personalization with Applications to Federated Learning [68.19709953755238]
  We present a systematic learning-theoretic study of personalization. We provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance. All of our algorithms are model-agnostic and work for any hypothesis class.
  arXiv  Detail & Related papers  (2020-02-25T01:36:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.